Senior Applied Scientist, Credit Risk

What You'll Do

• Design, build, and optimize machine learning models that support credit risk decisioning and portfolio management at Ramp
• Own the full applied science development lifecycle, from data exploration and feature development to model prototyping, deployment, monitoring, and iteration
• Investigate and evaluate new data sources, including structured and unstructured data, and integrate them into credit models where appropriate
• Develop backtesting, validation, and monitoring frameworks to evaluate model performance and business impact
• Apply methods from machine learning, statistics, causal inference, optimization, and economics to solve core business problems
• Generate and communicate data-driven insights that influence product, risk, and company strategy
• Partner with product, business, engineering, and data stakeholders to translate ambiguous problems into clear objectives, scoped opportunities, and a practical applied science roadmap
• Contribute to best practices for model development, experimentation, documentation, testing, and production reliability

What You Need

• Bachelor’s degree or above in Math, Economics, Bioinformatics, Statistics, Engineering, Computer Science, or other quantitative fields
• 5+ years of industry experience as an Applied Scientist, Machine Learning Engineer, Research Scientist, or equivalent; or 3+ years of industry experience with a PhD
• Strong familiarity with the mathematical fundamentals of advanced statistics, machine learning, optimization, and/or economics
• Experience working with large datasets using Python and SQL
• Strong Python experience across exploratory data analysis, predictive modeling, and applied machine learning, using tools such as NumPy, pandas, scikit-learn, PyTorch, or similar libraries
• Strong communication: the ability to bridge technical methodology to meaningful data narratives to drive company decisions and strategy
• Track record of shipping high-quality machine learning products in production and at scale
• Ability to thrive in a fast-paced, constantly improving, start-up environment that focuses on solving problems with iterative technical solutions

Nice-to-Haves

• PhD in Math, Economics, Bioinformatics, Statistics, Engineering, Computer Science, or other quantitative fields
• Strong perspective on data science engineering development cycle (data modeling, version control, documentation + testing, best practices for codebase development)
• Familiarity with data orchestration platforms (Airflow, Dagster, Prefect)
• Experience at a high-growth startup
• Experience leveraging AI/LLMs for development or for internal workflows